激光与光电子学进展, 2020, 57 (22): 221022, 网络出版: 2020-11-10
基于Mean Shift的背景梯度修正直方图跟踪算法 下载: 691次
Background Gradient Corrected Histogram Tracking Algorithm Based on Mean Shift
图像处理 目标跟踪 背景梯度 背景波动 背景加权直方图 image processing target tracking background gradient background fluctuation background weighted histogram
摘要
当图像中的背景发生波动时,修正的背景加权直方图(CBWH)算法在目标跟踪过程中存在波动跟随现象,从而产生波动误差。为了改善背景波动下算法的跟踪效果,减小波动误差,在CBWH算法的基础上提出了一种背景梯度修正直方图(BGCH)算法。利用相邻帧的背景梯度信息对目标模型进行二阶加权修正,提前阻断了CBWH算法的波动跟随过程。实验结果表明,本算法可以减小CBWH算法的波动误差,且对目标形变、模糊的情况,也表现出了更好的鲁棒性。
Abstract
When background fluctuates in the image, the target tracking process will follow the fluctuation of background with corrected background-weighted histogram (CBWH) algorithm, which will cause fluctuation-errors. In order to improve the tracking effect under fluctuant background and reduce the fluctuation-errors, this paper proposes a background gradient corrected histogram (BGCH) algorithm based on CBWH algorithm. It uses the background gradient information of adjacent frames to perform a second-order correction on the target model, and blocks the fluctuation-following process of the CBWH algorithm in advance. Experimental results show that this method significantly reduces the fluctuation-errors of CBWH algorithm, and also shows better robustness under the condition of target deforming and blurring.
喻璐璐, 谭逢富, 陈修涛, 秦来安, 侯再红. 基于Mean Shift的背景梯度修正直方图跟踪算法[J]. 激光与光电子学进展, 2020, 57(22): 221022. Lulu Yu, Fengfu Tan, Xiutao Chen, Laian Qin, Zaihong Hou. Background Gradient Corrected Histogram Tracking Algorithm Based on Mean Shift[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221022.